Github Copilot Cli
Analysis
This is a coherent instruction-only guide for using GitHub Copilot CLI, with expected caution around sharing code context with Copilot and relying on an undeclared local CLI dependency.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
gh copilot suggest "Add logging when translation fallback is used" --path services/translation
The skill instructs use of local Copilot CLI commands to generate or review code-related suggestions. This is central to the stated purpose and is scoped to paths, but users should still review outputs before applying changes.
gh copilot suggest "As a backend engineer, propose a minimal fix for mixed-language carryover" --path src/
The skill depends on the `gh copilot` command, while the provided metadata declares no required binaries and no install spec. This is an under-declared dependency rather than hidden code.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
gh copilot explain "What does this service do?" --path src/
The workflow sends or provides local code-path context to GitHub Copilot CLI for analysis. This is expected for the skill, but it can involve private source code or project context.
